wayback_machine_downloader 1.1.0 → 1.1.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/lib/wayback_machine_downloader.rb +4 -1
- metadata +1 -1
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA1:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: 6dd3fa14db3c1b3f109fec3ac2944d02118d2341
|
|
4
|
+
data.tar.gz: e1484e0f535d1c9bdb6f4de06a94028a422bf690
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 25e2fea35c30b509d29e17b7c74489a0c641cd278632ed942a8e398d059701d0b39e49f0aac0c94eb609a53655e5ec5de2917b4a62336b8763ef8bbba808de11
|
|
7
|
+
data.tar.gz: f7e5c53a62cf1091963be758904365a82de9d255605bd6a189a2d0bdf809667274fc48885cae2360094caaf3a4d5a66917c956065af747396d33028f124a5913
|
|
@@ -13,7 +13,7 @@ class WaybackMachineDownloader
|
|
|
13
13
|
|
|
14
14
|
include ArchiveAPI
|
|
15
15
|
|
|
16
|
-
VERSION = "1.1.
|
|
16
|
+
VERSION = "1.1.1"
|
|
17
17
|
|
|
18
18
|
attr_accessor :base_url, :directory, :from_timestamp, :to_timestamp, :only_filter, :exclude_filter, :all, :list, :maximum_pages, :threads_count
|
|
19
19
|
|
|
@@ -77,10 +77,13 @@ class WaybackMachineDownloader
|
|
|
77
77
|
end
|
|
78
78
|
|
|
79
79
|
def get_all_snapshots_to_consider
|
|
80
|
+
# Note: Passing a page index parameter allow us to get more snapshot, but from a less fresh index
|
|
80
81
|
print "Getting snapshot pages"
|
|
81
82
|
snapshot_list_to_consider = ""
|
|
82
83
|
snapshot_list_to_consider += get_raw_list_from_api(@base_url, nil)
|
|
83
84
|
print "."
|
|
85
|
+
snapshot_list_to_consider += get_raw_list_from_api(@base_url + '/*', nil)
|
|
86
|
+
print "."
|
|
84
87
|
@maximum_pages.times do |page_index|
|
|
85
88
|
snapshot_list = get_raw_list_from_api(@base_url + '/*', page_index)
|
|
86
89
|
break if snapshot_list.empty?
|